sammon_data

sammon_data, a Python code which generates 6 files of test data for multivariate data clustering.

Usage:

sammon_data

Licensing:

The computer code and data files described and made available on this web page are distributed under the MIT license

Languages:

sammon_data is available in a MATLAB version and a Python version.

Related Data and Programs:

Reference:

1. Ronald Fisher,
   The use of multiple measurements in taxonomic problems,
   Annual Eugenics,
   Volume 7, part II, 1936, pages 179-188.
2. John Sammon,
   A nonlinear mapping for data structure analysis,
   IEEE Transactions on Computers,
   Volume C-18, Number 5, May 1969, pages 401-409.

Source Code:

• sammon_data.py, the source code.
• sammon_data.sh, runs the tests.
• sammon_data.txt, the output file.

• sammon_circle.txt, points on a circle.
• sammon_helix.txt, points on a helix.
• sammon_iris.txt, Fisher's iris data.
• sammon_linear.txt, points on a line.
• sammon_nonlinear.txt, points on a nonlinear curve.
• sammon_simplex.txt, points clustered around the vertices of a simplex.